Merge branch 'cont-metrics' of https://github.com/EleutherAI/lm-evaluation-harness into alt_worlds

lm_eval/tasks/bigbench/greedy_until/similarities_abstraction.yaml

-# Generated by utils.py
-dataset_name: similarities_abstraction_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_similarities_abstraction_greedy_until

lm_eval/tasks/bigbench/greedy_until/simp_turing_concept.yaml

-# Generated by utils.py
-dataset_name: simp_turing_concept_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_simp_turing_concept_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_arithmetic_json.yaml

-# Generated by utils.py
-dataset_name: simple_arithmetic_json_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_simple_arithmetic_json_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_arithmetic_json_multiple_choice.yaml

-# Generated by utils.py
-dataset_name: simple_arithmetic_json_multiple_choice_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_simple_arithmetic_json_multiple_choice_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_arithmetic_json_subtasks.yaml

-# Generated by utils.py
-dataset_name: simple_arithmetic_json_subtasks_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_simple_arithmetic_json_subtasks_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_arithmetic_multiple_targets_json.yaml

-# Generated by utils.py
-dataset_name: simple_arithmetic_multiple_targets_json_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_simple_arithmetic_multiple_targets_json_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_ethical_questions.yaml

-# Generated by utils.py
-dataset_name: simple_ethical_questions_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_simple_ethical_questions_greedy_until

lm_eval/tasks/bigbench/greedy_until/simple_text_editing.yaml

-# Generated by utils.py
-dataset_name: simple_text_editing_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_simple_text_editing_greedy_until

lm_eval/tasks/bigbench/greedy_until/snarks.yaml

-# Generated by utils.py
-dataset_name: snarks_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_snarks_greedy_until

lm_eval/tasks/bigbench/greedy_until/social_iqa.yaml

-# Generated by utils.py
-dataset_name: social_iqa_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_social_iqa_greedy_until

lm_eval/tasks/bigbench/greedy_until/social_support.yaml

-# Generated by utils.py
-dataset_name: social_support_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_social_support_greedy_until

lm_eval/tasks/bigbench/greedy_until/sports_understanding.yaml

-# Generated by utils.py
-dataset_name: sports_understanding_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_sports_understanding_greedy_until

lm_eval/tasks/bigbench/greedy_until/strange_stories.yaml

-# Generated by utils.py
-dataset_name: strange_stories_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_strange_stories_greedy_until

lm_eval/tasks/bigbench/greedy_until/strategyqa.yaml

-# Generated by utils.py
-dataset_name: strategyqa_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_strategyqa_greedy_until

lm_eval/tasks/bigbench/greedy_until/sufficient_information.yaml

-# Generated by utils.py
-dataset_name: sufficient_information_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_sufficient_information_greedy_until

lm_eval/tasks/bigbench/greedy_until/suicide_risk.yaml

-# Generated by utils.py
-dataset_name: suicide_risk_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_suicide_risk_greedy_until

lm_eval/tasks/bigbench/greedy_until/swahili_english_proverbs.yaml

-# Generated by utils.py
-dataset_name: swahili_english_proverbs_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_swahili_english_proverbs_greedy_until

lm_eval/tasks/bigbench/greedy_until/swedish_to_german_proverbs.yaml

-# Generated by utils.py
-dataset_name: swedish_to_german_proverbs_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_swedish_to_german_proverbs_greedy_until

lm_eval/tasks/bigbench/greedy_until/symbol_interpretation.yaml

-# Generated by utils.py
-dataset_name: symbol_interpretation_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_symbol_interpretation_greedy_until

lm_eval/tasks/bigbench/greedy_until/temporal_sequences.yaml

-# Generated by utils.py
-dataset_name: temporal_sequences_zero_shot
-include: ../greedy_until_template_yaml
-task: bigbench_temporal_sequences_greedy_until